"How to Enable Voice Typing on My Computer" matching MCP servers:

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Enables a constrained subagent to perform foreground GUI actions on Hyprland—observing, focusing windows, clicking, typing, scrolling, dragging, and managing the clipboard—under per-action approval with lease, audit log, and kill-switch gating.

Enables Alexa+ clients to monitor live calls for voice-clone and scam-pressure risk, verify a caller with a real family member, review alert history, and reset call state through MCP tools.

Enables AI agents to automate macOS desktop GUI applications through a policy-governed MCP proxy over Cua Driver, with fail-closed per-app allowlisting, a hardcoded sensitive-app denylist, an emergency kill-switch, masked audit logging, and self-healing app recovery with durable task journaling.

Enables management of system users through a simple API, exposing two MCP tools that forward authentication headers to the upstream service.

Enables secure chat-based interaction with PostgreSQL databases through Claude Desktop. Features GitHub OAuth authentication, role-based access control, and enterprise-grade security for database queries and operations.

Enables management of system users through a simple sample API, exposed as MCP tools for natural-language interaction.

An MCP server template with built-in OAuth 2.0 authorization code flow and PKCE, enabling Grok to authenticate and invoke tools such as hello and publish_page.

An MCP Server that enables users to interact with Google's On-Demand Scanning API (v1beta1) through natural language, likely providing capabilities for vulnerability scanning and security analysis of containers and artifacts.

Enables management of system users through a simple sample API, with support for HTTP and stdio transports and forwarding of authentication headers.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

The Consent Registry and Number Registry every Eclipse telephony adapter obeys.

Enables AI agents to search, read, and write a shared tree of markdown articles hosted on Amazon S3, with per-folder and per-article permissions, attribution of every change to the signed-in user, and full version history. Agents get exactly the access granted to the person they act for, and cannot grant permissions or hard-delete content.

Enables AI agents to enroll and verify voice samples against known identities, providing honest confidence signals about voice authenticity.

Enables AI agents to interact with an Odoo ERP through tool calls that are allowlist-policy-checked, risk-scored and throttled before touching the ERP, covering record reads, writes, deletes and method execution. Every request and decision is recorded to a hash-chained, tamper-evident audit log with optional HMAC keys and anchor exports.

Connects AI assistants to the Vectra AI On-Premise security platform for natural language threat detection, investigation, and automated incident response workflows.

Enables deployment of an MCP server on Cloudflare Workers with OAuth login, allowing remote invocation of tools like math operations from MCP clients.

Enables AgentBase agents to call read-only tools for employee directory, leave balances, purchase orders, and inventory levels while keeping enterprise data inside the data center.

Enables AI agents to perform human-authorized, fully auditable GUI actions — clicking, typing, and window operations — on a local Windows desktop, gated by time- and count-limited leases that are denied by default until a person signs off in a popup. Every action is bound to a fresh screen capture, leaves screenshot-based evidence and decision logs on the local machine, and can be halted instantly via a panel button, hotkey, or kill-switch file.

Enables MCP clients to exchange an MCP-audience token for a Microsoft Graph token and call Graph as the signed-in user, with tools for identity verification and recent mail access.

A remote MCP server deployed on Cloudflare Workers with OAuth authentication, enabling secure tool calling over SSE.

Enables deploying a remote MCP server on Cloudflare Workers with OAuth login, allowing MCP clients like Claude Desktop to connect and use tools over SSE.

Demonstrates an MCP server with a vulnerable add tool protected by SonnyLabs prompt injection detection.

Stateless Streamable HTTP MCP endpoint with OAuth 2.1 authentication via Cloudflare Workers, supporting PKCE, DCR, and token introspection.

An MCP server deployed on Cloudflare Workers with OAuth login, allowing remote invocation of tools like math operations from MCP-compatible clients.

Audits Ethereum/Solidity smart contracts using the Cysic Minimax model, providing automated vulnerability detection, gas optimization suggestions, and markdown report generation.

Enables creating and managing workspaces, attaching records, inviting participants, and retrieving verification and receipt lookups through tools.

Enables Claude Desktop to use MCP tools hosted in Azure Container Apps, secured with Microsoft Entra ID sign-in, and provides hello and whoami tools to confirm connectivity and the signed-in Microsoft account.

Enables chatting with PostgreSQL databases via MCP tools, with GitHub OAuth authentication and role-based write access, deployable on Cloudflare Workers.

A hardened MCP server that enforces authentication via Easy Auth and OAuth, manages secrets with Key Vault, and restricts network access using VNet integration and API Management, enabling secure tool invocations through a fully private infrastructure.